ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction

TL;DR

ChemBERTa demonstrates that transformer models, pretrained on large molecular datasets, can effectively predict molecular properties, offering a promising alternative to traditional methods like GNNs and fingerprints.

Contribution

This work systematically evaluates transformers for molecular property prediction and introduces ChemBERTa, a large-scale pretrained model with a new dataset of 77 million SMILES for self-supervised learning.

Findings

ChemBERTa scales well with dataset size

Achieves competitive performance on MoleculeNet

Provides attention-based visualization tools

Abstract

GNNs and chemical fingerprints are the predominant approaches to representing molecules for property prediction. However, in NLP, transformers have become the de-facto standard for representation learning thanks to their strong downstream task transfer. In parallel, the software ecosystem around transformers is maturing rapidly, with libraries like HuggingFace and BertViz enabling streamlined training and introspection. In this work, we make one of the first attempts to systematically evaluate transformers on molecular property prediction tasks via our ChemBERTa model. ChemBERTa scales well with pretraining dataset size, offering competitive downstream performance on MoleculeNet and useful attention-based visualization modalities. Our results suggest that transformers offer a promising avenue of future work for molecular representation learning and property prediction. To facilitate these efforts, we release a curated dataset of 77M SMILES from PubChem suitable for large-scale self-supervised pretraining.